Skip to main content
The Python SDK is the primary way to integrate DecimalAI into your agent code. It wraps every public REST endpoint, auto-instruments 8 agent framework integrations plus 3 direct LLM provider SDKs (OpenAI, Anthropic, Google) — including native plugins for Google ADK and Anthropic’s Claude Agent SDK — and ships zero-config helpers for tracing, evaluation, and dataset export. 
pip install decimalai

import decimalai
decimalai.init(api_key="dai_sk_...", openai_agents=True)
# Every supported framework call is now traced.

​
Sections

Init & Setup

decimalai.init(), environment variables, framework flags.

Tracing

@trace, start_trace, log_llm_call, log_tool_call, @tool.

Manifests

register_manifest, flush_manifest_for_ci.

Evaluations

eval, score, get_eval_breakdown, batch_eval, @eval, external imports.

Replay & Experiments

get_replay_prompts, create_replay_batch, get_replay_batch.

Datasets & Training

pull_dataset, push_to_hub, load_hf_dataset.

Framework Instrumentation

8 framework integrations — OpenAI Agents, LangChain, LlamaIndex, CrewAI, AutoGen, generic OTel, plus native plugins for Google ADK and Anthropic Claude Agent SDK.

Skills

Sync from disk, pull from platform, SkillRouter CRUD.

​
Complete API Summary

​
Top-level functions (in decimalai)

Grouped by surface. Every function below is importable directly from decimalai.
MethodDescription
init()Initialize SDK and auto-instrument frameworks.
@trace()Decorator to trace a function as an agent run.
start_trace()Context manager for manual trace boundaries.
log_llm_call()Log an LLM call inside a trace.
log_tool_call()Log a tool call inside a trace.
@toolDecorator to register a tracked tool.
send()Send a fully-constructed trace payload.
MethodDescription
register_manifest()Explicitly register agent configuration.
flush_manifest_for_ci()Capture and write the manifest ID for the regression-check Action.
MethodDescription
eval()Pushes a single named score to a trace (alias of score()). The custom-evaluator decorator is @decimalai.evals.eval, not this top-level function.
score()Push a single named score to a trace.
batch_eval()Apply evaluators across multiple traces in parallel.
get_eval_breakdown()Get full eval breakdown for a trace.
push_deepeval_results()Import DeepEval scores.
push_langsmith_scores()Import LangSmith feedback as eval scores.
push_custom_scores()Push scores from any source.
MethodDescription
pull_dataset()Materialize a dataset version as a HuggingFace Dataset.
push_to_hub()Push a dataset to HuggingFace Hub.
load_hf_dataset()Convenience loader returning a datasets.Dataset.
MethodDescription
get_replay_prompts()Download stale prompts for replay.
create_replay_batch()Create a batch of replay tasks.
get_replay_batch()Check replay batch progress.
submit_replay_result()Submit a replayed trace result.

​
Framework instrumentation (subpackages)

8 framework integrations. Google ADK and Anthropic’s Claude Agent SDK use native plugins (not OTel).
ModuleFunctionUse it for
decimalai.langchaininstall()LangChain / LangGraph callbacks
decimalai.openai_agentsinstall(agent=...)OpenAI Agents SDK — pass the Agent object for full schema introspection
decimalai.llamaindexinstall()LlamaIndex span handler
decimalai.crewaiinstall()CrewAI via OpenTelemetry
decimalai.autogeninstall()AutoGen / AG2 via OpenTelemetry
decimalai.adkinstall()Google ADK — native plugin (Gemini-native)
decimalai.claude_agent_sdkinstall()Anthropic Claude Agent SDK — native plugin
decimalai.otelinstall()Generic OpenTelemetry GenAI span exporter

​
Class-based clients

ClassUse it for
SkillRouter (from decimalai)Registry + skill lifecycle: fork (workspace copy), install (fork + write to disk), preview (read-only snapshot), create_skill, list_skills, get_skill, update_skill, delete_skill, sync_skills, list_versions, get_menu, smart_route, export_to_disk, pull_missing.

​
REST-only endpoints

For endpoints that don’t yet have a top-level SDK wrapper (list_datasets, get_trace_stats, get_manifest, repair preview/apply, compatibility policy set, etc.), use httpx directly against the REST API: 
import httpx

resp = httpx.get(
    "https://api.decimal.ai/api/v1/datasets",
    headers={"Authorization": "Bearer dai_sk_..."},
)
resp.raise_for_status()
See the API Reference for the full endpoint registry.